Patents Examined by Abdelali Serrou
  • Patent number: 10553199
    Abstract: A method of providing real-time speech synthesis based on user input includes presenting a graphical user interface having a low-dimensional representation of a multi-dimensional phoneme space, a first dimension representing degree of vocal tract constriction and voicing, a second dimension representing location in a vocal tract. One example employs a disk-shaped layout. User input is received via the interface and translated into a sequence of phonemes that are rendered on an audio output device. Additionally, a synthesis method includes maintaining a library of prerecorded samples of diphones organized into diphone groups, continually receiving a time-stamped sequence of phonemes to be synthesized, and selecting a sequence of diphone groups with their time stamps. A best diphone within each group is identified and placed into a production buffer from which diphones are rendered according to their time stamps.
    Type: Grant
    Filed: May 20, 2016
    Date of Patent: February 4, 2020
    Assignee: Trustees of Boston University
    Inventors: Frank Harold Guenther, Alfonso Nieto-Castanon
  • Patent number: 10547936
    Abstract: The examples relate to implementations of apparatuses, such as lighting devices, and a system that uses a speech-based user interface to provide speech-based navigation services. The speech-based user interface provides navigation instructions that direct a person to the location of an item within a premises. The person interacts with a speech-based apparatus to receive the navigation instructions as speech-based directions through the premises from a specified location to the item location, or as static navigation instructions enabling the person to navigate from the specified location to the item location. A directional microphone and a controllable speaker receive audio inputs from and output audio outputs to a specified location or subarea of the premises to a person using the speech-based user interface. The audio outputs are directed to the person in the subarea of the premises, and have a higher amplitude within the subarea than outside the subarea of the premises.
    Type: Grant
    Filed: June 23, 2017
    Date of Patent: January 28, 2020
    Assignee: ABL IP HOLDING LLC
    Inventors: Vernon J. Nagel, Jenish S. Kastee, Jack C. Rains, Jr., Nathaniel W. Hixon, Youssef F. Baker, Daniel M. Megginson, Sean P. White, Niels G. Eegholm
  • Patent number: 10540439
    Abstract: Systems and methods for semantically analyzing digital information. A cognitive engine is configured to determine useful evidentiary information from large digital content data sets. Further, the cognitive engine can analyze or manipulate the evidentiary information to derive data needed to solve problems, identify issues, and identify patterns. The results can then be applied to any application, interface, or automation as appropriate.
    Type: Grant
    Filed: April 17, 2017
    Date of Patent: January 21, 2020
    Assignee: MARCA RESEARCH & DEVELOPMENT INTERNATIONAL, LLC
    Inventors: Mahmoud Azmi Khamis, Bruce Golden, Rami Ikhreishi
  • Patent number: 10515150
    Abstract: A method for configuring an automated, speech driven self-help system based on prior interactions between a plurality of customers and a plurality of agents includes: recognizing, by a processor, speech in the prior interactions between customers and agents to generate recognized text; detecting, by the processor, a plurality of phrases in the recognized text; clustering, by the processor, the plurality of phrases into a plurality of clusters; generating, by the processor, a plurality of grammars describing corresponding ones of the clusters; outputting, by the processor, the plurality of grammars; and invoking configuration of the automated self-help system based on the plurality of grammars.
    Type: Grant
    Filed: July 14, 2015
    Date of Patent: December 24, 2019
    Inventors: Yoni Lev, Tamir Tapuhi, Avraham Faizakof, Amir Lev-Tov, Yochai Konig
  • Patent number: 10515646
    Abstract: A quantization apparatus comprises: a first quantization module for performing quantization without an inter-frame prediction; and a second quantization module for performing quantization with an inter-frame prediction, and the first quantization module comprises: a first quantization part for quantizing an input signal; and a third quantization part for quantizing a first quantization error signal, and the second quantization module comprises: a second quantization part for quantizing a prediction error; and a fourth quantization part for quantizing a second quantization error signal, and the first quantization part and the second quantization part comprise a trellis structured vector quantizer.
    Type: Grant
    Filed: March 30, 2015
    Date of Patent: December 24, 2019
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventor: Ho-sang Sung
  • Patent number: 10503469
    Abstract: Embodiments of the invention provide for secure voice authentication through a communication device or access device. Certain embodiments allow for providing a word string to a communication device or authentication device. The communication or authentication device plays a supplemental signal that is unique to a transaction. The communication device or authentication device concurrently records an audio segment originating from the user and the supplemental signal. The audio segment is an attempt by the user to vocally reproduce the word string. The communication device or authentication device sends the concurrently recorded audio segment and supplemental signal, to a computer, where the computer authenticates the user.
    Type: Grant
    Filed: December 12, 2017
    Date of Patent: December 10, 2019
    Assignee: Visa International Service Association
    Inventors: Robert Rutherford, Julian Hua
  • Patent number: 10482184
    Abstract: A method for context-based natural language processing is disclosed herein. The method comprises maintaining a plurality of dialog system rules, receiving a user request from a Dialog System Interface, receiving one or more attributes associated with the user request from the Dialog System Interface or a user device, and identifying a type of context associated with the user request based on the user request and the one or more attributes. A context label is assigned to the user request associated with the type of context. Based on the context label and the user request, a particular dialog system rule is selected from the plurality of dialog system rules. A response to the user request is generated by applying the dialog system rule to at least a part of the user request.
    Type: Grant
    Filed: March 8, 2016
    Date of Patent: November 19, 2019
    Assignee: GOOGLE LLC
    Inventors: Ilya Gennadyevich Gelfenbeyn, Artem Goncharuk, Pavel Aleksandrovich Sirotin
  • Patent number: 10460746
    Abstract: A process for real-time language detection and language heat map data structure modification includes a computing device receiving, from a first electronic audio source, first audio content and identifying a first geographic location of the first audio content. The computing device then determines that the first audio content includes first speech audio and identifies a first language in which the first speech audio is spoken. A first association is created between the first geographic location and the first language, and a real-time language heat-map data structure modified to include the created first association. Then a further action is taken by the computing device as a function of the modified real-time language heat-map data structure.
    Type: Grant
    Filed: October 31, 2017
    Date of Patent: October 29, 2019
    Assignee: MOTOROLA SOLUTIONS, INC.
    Inventors: Fabio M. Costa, Alejandro G. Blanco, Patrick D. Koskan, Adrian Ho Yin Ng, Boon Beng Lee
  • Patent number: 10446134
    Abstract: A system and method for identifying special information within a voice recording is provided. Training to identify a speaker is performed. A voice recording including utterances by at least two speakers is processed to identify segments of the voice recording provided by the speaker. Remaining segments of the voice recording are designated as provided by another speaker. A text element that corresponds to a request for information is identified in at least one of the segments of the voice recording provided by the speaker. A predetermined duration associated with the identified text element is applied to one of the segments of the voice recording of the other speaker occurring immediately after the segment of the voice recording from the regular speaker with the identified text element. The utterances from the other speaker occurring within the predetermined duration are identified as special information and rendered unintelligible.
    Type: Grant
    Filed: January 29, 2018
    Date of Patent: October 15, 2019
    Assignee: Intellisist, Inc.
    Inventors: Howard M. Lee, Steven Lutz, Gilad Odinak
  • Patent number: 10437935
    Abstract: The disclosed technology for accurate translation of elements in a web application includes systems and methods that provide a sanitization and exception-generation tool set configurable to present tags in a preliminary localization kit to a localization expert; and run a tag name convention enforcement tool against the preliminary localization kit, which parses extracted tags and locates key name strings and translatable text, then applies key naming rules that require presence of keywords from a list of valid keywords and that require key uniqueness. The tool set creates bug report stubs from a tag exception and accepts additional comments from the expert to include in a completed bug report, regarding the key name that triggered the exception; is configurable to generate sanitization correction files using the received key names and edited translatable text for processing by a developer; and includes a verification-in-context tool that supports debugging of a language pack.
    Type: Grant
    Filed: April 18, 2017
    Date of Patent: October 8, 2019
    Assignee: salesforce.com, inc.
    Inventors: Cornelia Sittel, Hendrik Lipka
  • Patent number: 10430157
    Abstract: A speech recognition method and apparatus are provided, in which the speech recognition apparatus may recognize a user feature and a speech recognition environment, determine a speech recognition speed for performing speech recognition based on one of the recognized user feature and the speech recognition environment, and perform the speech recognition based on the determined speech recognition speed.
    Type: Grant
    Filed: July 14, 2015
    Date of Patent: October 1, 2019
    Assignee: Samsung Electronics Co., Ltd.
    Inventor: Hoshik Lee
  • Patent number: 10410627
    Abstract: A method for generating a speech recognition model includes accessing a baseline speech recognition model, obtaining information related to recent language usage from search queries, and modifying the speech recognition model to revise probabilities of a portion of a sound occurrence based on the information. The portion of a sound may include a word. Also, a method for generating a speech recognition model, includes receiving at a search engine from a remote device an audio recording and a transcript that substantially represents at least a portion of the audio recording, synchronizing the transcript with the audio recording, extracting one or more letters from the transcript and extracting the associated pronunciation of the one or more letters from the audio recording, and generating a dictionary entry in a pronunciation dictionary.
    Type: Grant
    Filed: March 15, 2018
    Date of Patent: September 10, 2019
    Assignee: Google LLC
    Inventors: Michael H. Cohen, Shumeet Baluja, Pedro J. Moreno Mengibar
  • Patent number: 10410630
    Abstract: A system provides multi-modal user interaction. The system is configured to detect acoustic events to perform context-sensitive personalized conversations with the speaker. Conversation or communication among the speakers or devices is categorized into different classes as confidential, partially anonymous, or public. When exchange with cloud infrastructure is needed, a clear indicator is presented to the speaker via one or more modalities. Furthermore, different dialog strategies are employed in situations where conversation failures, such as misunderstanding, wrong expectation, emotional stress, or memory deficiencies, occur.
    Type: Grant
    Filed: June 19, 2015
    Date of Patent: September 10, 2019
    Assignee: Robert Bosch GmbH
    Inventors: Fuliang Weng, Katrin Schulze, Zhongnan Shen, Pongtep Angkititrakul, Gengyan Bei, Xiao Xiong
  • Patent number: 10403295
    Abstract: The present invention proposes a new method and a new apparatus for enhancement of audio source coding systems utilizing high frequency reconstruction (HFR). It utilizes a detection mechanism on the encoder side to assess what parts of the spectrum will not be correctly reproduced by the HFR method in the decoder. Information on this is efficiently coded and sent to the decoder, where it is combined with the output of the HFR unit.
    Type: Grant
    Filed: August 18, 2016
    Date of Patent: September 3, 2019
    Assignee: Dolby International AB
    Inventors: Kristofer Kjoerling, Per Ekstrand, Holger Hoerich
  • Patent number: 10332531
    Abstract: An apparatus for decoding an encoded audio signal having an encoded representation of a first set of first spectral portions and an encoded representation of parametric data indicating spectral energies for a second set of second spectral portions, has: an audio decoder for decoding the encoded representation of the first set of the first spectral portions to obtain a first set of first spectral portions and for decoding the encoded representation of the parametric data to obtain a decoded parametric data for the second set of second spectral portions indicating, for individual reconstruction bands, individual energies; a frequency regenerator for reconstructing spectral values in a reconstruction band having a second spectral portion using a first spectral portion of the first set of the first spectral portions and an individual energy for the reconstruction band, the reconstruction band having a first spectral portion and the second spectral portion.
    Type: Grant
    Filed: January 18, 2018
    Date of Patent: June 25, 2019
    Assignee: Fraunhofer-Gesellschaft zur Foerderung der Angewandten Forschung e.V.
    Inventors: Andreas Niedermeier, Christian Ertel, Ralf Geiger, Florin Ghido, Christian Helmrich
  • Patent number: 10311892
    Abstract: An apparatus for decoding an encoded audio signal, includes a spectral domain audio decoder for generating a first decoded representation of a first set of first spectral portions, the decoded representation having a first spectral resolution; a parametric decoder for generating a second decoded representation of a second set of second spectral portions having a second spectral resolution being lower than the first spectral resolution; a frequency regenerator for regenerating every constructed second spectral portion having the first spectral resolution using a first spectral portion and spectral envelope information for the second spectral portion; and a spectrum time converter for converting the first decoded representation and the reconstructed second spectral portion into a time representation.
    Type: Grant
    Filed: December 7, 2017
    Date of Patent: June 4, 2019
    Assignee: Fraunhofer-Gesellschaft zur Foerderung der angewandten Forschung e.V.
    Inventors: Sascha Disch, Frederik Nagel, Ralf Geiger, Balaji Nagendran Thoshkahna, Konstantin Schmidt, Stefan Bayer, Christian Neukam, Bernd Edler, Christian Helmrich
  • Patent number: 10296733
    Abstract: In one aspect, a method includes receiving an identifier; obtaining a plurality of prompts using the identifier, wherein a first prompt corresponds to a first character of an access code, and a second prompt corresponds to a second character of the access code; causing the first prompt and the second prompt to be presented on a display at locations corresponding to a first alternative; causing third prompts and fourth prompts to be presented on the display at locations corresponding to a second alternative; receiving an audio signal comprising speech spoken by a user; and determining whether the audio signal comprises the user speaking the first prompt followed by the second prompt.
    Type: Grant
    Filed: July 13, 2015
    Date of Patent: May 21, 2019
    Assignee: Friday Harbor LLC
    Inventor: Derrick Raymond Roos
  • Patent number: 10276183
    Abstract: An apparatus for decoding an encoded audio signal having an encoded representation of a first set of first spectral portions and an encoded representation of parametric data indicating spectral energies for a second set of second spectral portions, has: an audio decoder for decoding the encoded representation of the first set of the first spectral portions to obtain a first set of first spectral portions and for decoding the encoded representation of the parametric data to obtain a decoded parametric data for the second set of second spectral portions indicating, for individual reconstruction bands, individual energies; a frequency regenerator for reconstructing spectral values in a reconstruction band having a second spectral portion using a first spectral portion of the first set of the first spectral portions and an individual energy for the reconstruction band, the reconstruction band having a first spectral portion and the second spectral portion.
    Type: Grant
    Filed: January 20, 2016
    Date of Patent: April 30, 2019
    Assignee: Fraunhofer-Gesellschaft zur Foerderung der angewandten Forschung e.V.
    Inventors: Andreas Niedermeier, Christian Ertel, Ralf Geiger, Florin Ghido, Christian Helmrich
  • Patent number: 10276184
    Abstract: An apparatus for decoding an encoded audio signal, includes a spectral domain audio decoder for generating a first decoded representation of a first set of first spectral portions, the decoded representation having a first spectral resolution; a parametric decoder for generating a second decoded representation of a second set of second spectral portions having a second spectral resolution being lower than the first spectral resolution; a frequency regenerator for regenerating every constructed second spectral portion having the first spectral resolution using a first spectral portion and spectral envelope information for the second spectral portion; and a spectrum time converter for converting the first decoded representation and the reconstructed second spectral portion into a time representation.
    Type: Grant
    Filed: January 20, 2016
    Date of Patent: April 30, 2019
    Assignee: Fraunhofer-Gesellschaft zur Foerderung der angewandten Forschung e.V.
    Inventors: Sascha Disch, Frederik Nagel, Ralf Geiger, Balaji Nagendran Thoshkahna, Konstantin Schmidt, Stefan Bayer, Christian Neukam, Bernd Edler, Christian Helmrich
  • Patent number: 10249297
    Abstract: Examples of the present disclosure describe processing by an input understanding system/service. A received input is processed to generate a set of alternatives for recognizing the received input. The set of alternatives is filtered. Filtering comprises ranking the set of alternatives and propagating a plurality of the ranked alternatives for additional processing. The propagated alternatives are processed to generate an expanded set of alternatives for potential hypotheses based on the received input. The expanded set of alternatives is filtered. Filtering comprises ranking alternatives of the expanded set and propagating a plurality of the ranked alternatives of the expanded set for additional processing. The propagated alternatives of the expanded set are evaluated based on application of knowledge data fetched from external resources. A response to the received input is generated.
    Type: Grant
    Filed: July 13, 2015
    Date of Patent: April 2, 2019
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Omar Zia Khan, Ruhi Sarikaya